Agent37 runs AI agent sandboxes for under 10% of typical cost
Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents
Agent37, a YC F26 startup, offers sandboxes for AI agents at under 10% of typical provider costs, with customers spending an average of $0.37 per month per sandbox. Founder Vishnu, a former Amazon engineer, explains how they cut costs by managing bursty CPU/RAM usage, renting from Hetzner and OVH instead of hyperscalers, using gVisor for resource sharing, and optimizing hosts for RAM. The free plan now hosts over 90% of new signups, with infrastructure costs of $0.05–$0.10 per user per month.
I worked at Amazon before and they have 80-90% margins on VMs. So it was an obvious choice once I looked at the prices to go one layer down to vendors like Hetzner and OVH.
- mparis
Congrats on the launch! Very exciting!
You guys are operating in a very competitive space. This stuff is fun to build, so a lot of engineers will end up building it. Not to discourage you, but I suspect it will be difficult to capture much value selling this offering as its going to be race to the bottom against very well funded alternatives that can sell these features at a loss in order to get you to use their databases and other offerings that are higher margin and stickier.
As you guys learn more about how to take this sort of technology to market, you may consider trying to get closer to the actual work that people actually need these agents to do. What can you do better because you have this technology? For example, I work in healthcare administration and we have built our own agent sandbox infrastructure on top of firecracker microvms that solve similar use cases as Agent37. We will never sell it. It's part of our competitive advantage for doing healthcare tasks.
Food for thought! Good luck!
- gexla
Nice, you caught my eyeballs at the right time. I'm going to sign up for it. Cursor / GrokBot already gives me this, but I'm looking to recreate this setup as a backup so that I don't get locked in. This feels like the right direction. Move all this stuff off my desktop and then run everything from my phone.
- itissid
Congrats on the launch!. Looks awesome. One small gripe I have is that the user success stores seems obviously like claude has written them. I cancelled my claude sub for codex, partly because i cannot understand claude's style at all - not that there is anything is wrong with it, its effing incomprehensible.
Compare the two yourself and judge(latter is written in gpt-6 luna).
> One client is one API call. It comes back as an always-on Hermes agent that holds that client’s data, that client’s identity, and a hard ceiling on what it can spend. It answers on an OpenAI-compatible endpoint from the moment it boots, so integrating it was a base URL, the same as pointing at any model API.
> Boon provisions an agent for a client with one API call. Each agent has its own client data and identity, along with a spending limit. It exposes an OpenAI-compatible endpoint, so Boon can connect to it by configuring a base URL.
- alasano
I've been looking at offloading local work from my MacBook Pro (M1 Pro / 32 GB) specifically because I've been working with a lot of Android apps and emulation is killing me on top of everything else that I'm running.
Got a bunch of Daytona credits which are close to useless given their restrictions until you hit tier 3.
You seem like you're actually slightly cheaper than https://boat.dev/ but with less storage? That's the closest to your pricing unless I'm mistaken. Any other insight as to differences between you two?
Also I'll add you to a list I've been maintaining of sandbox providers, congrats on the launch!
- asadm
Is this using cloudflare behind the scene? how does it compare with https://agents.cloudflare.com/